Defending Your Mobile Fortress: An In-Depth Look at on-Device Trojan Detection in Machine Learning: Systematic Literature Review

Abstract

Mobile app trojans are becoming an increasingly serious threat to personal information security. They can cause severe damage by exposing sensitive and personally-identifying information to malicious actors. This paper’s contribution is a comprehensive review of the attack vectors for trojan attacks, and ways to eliminate the risks posed by attack vectors and generate settlement automatically. As such, such attacks must be prevented. In this study, we explore to find how to detect the trojan attack in detail, and the way that we know in machine learning. A review is conducted on the state-of-the-art methods using the preferred reporting items for reviews and meta-analyses (PRISMA) guidelines. We review literature from several publications and analyze the use of machine learning for on-device trojan detection. This review provides evidence for the effectiveness of machine learning in detecting such threats. The current trend shows that signature-based analysis using various metadata, such as permission, intent, API and system calls, and network analysis, are capable of detecting trojan attacks before and after the initial infection